pythonpackage.yml

name: Struo2

on:
  push:
    branches: [ master ]
  pull_request:
    branches: [ master ]

jobs:
  build:
    name: build (${{ matrix.python-version }}, ${{ matrix.os }})
    runs-on: ubuntu-latest
    env:
      DATADIR: data
    strategy:
      matrix:
        python-version: [3.7]
    steps:
    - uses: conda-incubator/setup-miniconda@v2
      with:
        miniconda-version: 'latest'
        auto-update-conda: true
        python-version: ${{ matrix.python-version }}
        channels: conda-forge,bioconda
        channel-priority: strict
        activate-environment: struo2
    - name: Checkout repository
      uses: actions/checkout@v2
    - name: Checkout submodules
      run: git submodule update --init --recursive
    - name: conda env setup
      shell: bash -l {0}
      run: |
        conda info -a
        conda env update -f conda_env.yaml python=${{ matrix.python-version }}
        conda list
    - name: taxdump db setup
      shell: bash -l {0}
      run: |
        mkdir -p $DATADIR
        wget --directory-prefix $DATADIR http://ftp.tue.mpg.de/ebio/projects/struo2/GTDB_release95/taxdump/taxdump.tar.gz
        tar -pzxvf $DATADIR/taxdump.tar.gz --directory $DATADIR
    - name: UniRef db setup
      shell: bash -l {0}
      run: |
        mkdir -p $DATADIR/UniRef90/
        touch $DATADIR/UniRef90/uniref90 $DATADIR/UniRef90/uniref90.dbtype $DATADIR/UniRef90/uniref90.index
        touch $DATADIR/UniRef90/uniref90.lookup $DATADIR/UniRef90/uniref90.source
        touch $DATADIR/UniRef90/uniref90_h $DATADIR/UniRef90/uniref90_h.dbtype $DATADIR/UniRef90/uniref90_h.index
        wget --directory-prefix $DATADIR http://ftp.tue.mpg.de/ebio/projects/struo2/install/uniref_2019.01/uniref50-90.pkl
    - name: Reference genome download
      shell: bash -l {0}
      run: |
        wget --directory-prefix $DATADIR http://ftp.tue.mpg.de/ebio/projects/struo2/dev_data/genomes/GTDBr95_n10.tar.gz
        tar -pzxvf $DATADIR/GTDBr95_n10.tar.gz --directory $DATADIR
    - name: DB create tests
      shell: bash -l {0}
      run: |
        snakemake --use-conda --configfile config.yaml -j 1 -F --dryrun
    - name: DB update tests
      shell: bash -l {0}
      run: |
        echo "todo" #snakemake --use-conda --configfile config-update.yaml -j 1 -F --dryrun
    - name: Util script dependency tests
      shell: bash -l {0}
      run: |
        ./util_scripts/genome_download.R -h
        ./util_scripts/GTDB_metadata_filter.R -h
        ./util_scripts/tree_prune.py -h
        ./util_scripts/genome_mis-asmbl_sim.py -h
    - name: Tree pruning test
      shell: bash -l {0}
      run: |
        wget --directory-prefix $DATADIR http://ftp.tue.mpg.de/ebio/projects/struo2/dev_data/phylogeny.tar.gz
        tar -pzxvf $DATADIR/phylogeny.tar.gz --directory $DATADIR
        ./util_scripts/tree_prune.py data/phylogeny/accs_to_keep.txt data/phylogeny/ar122_r95.tree
    - name: Mis-assembly simulation test
      shell: bash -l {0}
      run: |
        ./util_scripts/genome_mis-asmbl_sim.py -b 2 -r 2 -c 2 -T ncbi_organism_name -F fasta_file_path data/GTDBr95_n10/GTDBr95_n10.tsv